1
|
Deng Z, Tang J, Fang C, Zhang BH. Development and validation of a diagnostic prediction model for severe periventricular-intraventricular hemorrhage in newborns: insights from a retrospective analysis utilizing the MIMIC-III database. J Pediatr (Rio J) 2024; 100:327-334. [PMID: 38342483 PMCID: PMC11065675 DOI: 10.1016/j.jped.2023.12.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Revised: 12/27/2023] [Accepted: 12/28/2023] [Indexed: 02/13/2024] Open
Abstract
OBJECTIVE Periventricular-intraventricular hemorrhage is the most common type of intracranial bleeding in newborns, especially in the first 3 days after birth. Severe periventricular-intraventricular hemorrhage is considered a progression from mild periventricular-intraventricular hemorrhage and is often closely associated with severe neurological sequelae. However, no specific indicators are available to predict the progression from mild to severe periventricular-intraventricular in early admission. This study aims to establish an early diagnostic prediction model for severe PIVH. METHOD This study was a retrospective cohort study with data collected from the MIMIC-III (v1.4) database. Laboratory and clinical data collected within the first 24 h of NICU admission have been used as variables for both univariate and multivariate logistic regression analyses to construct a nomogram-based early prediction model for severe periventricular-intraventricular hemorrhage and subsequently validated. RESULTS A predictive model was established and represented by a nomogram, it comprised three variables: output, lowest platelet count and use of vasoactive drugs within 24 h of NICU admission. The model's predictive performance showed by the calculated area under the curve was 0.792, indicating good discriminatory power. The calibration plot demonstrated good calibration between observed and predicted outcomes, and the Hosmer-Lemeshow test showed high consistency (p = 0.990). Internal validation showed the calculated area under a curve of 0.788. CONCLUSIONS This severe PIVH predictive model, established by three easily obtainable indicators within the NICU, demonstrated good predictive ability. It offered a more user-friendly and convenient option for neonatologists.
Collapse
Affiliation(s)
- Zhiyue Deng
- Department of Neonatology, Renmin Hospital of Wuhan University, Wuhan, China
| | - Jiaxin Tang
- Department of Neonatology, Renmin Hospital of Wuhan University, Wuhan, China
| | - Chengzhi Fang
- Department of Neonatology, Renmin Hospital of Wuhan University, Wuhan, China
| | - Bing-Hong Zhang
- Department of Neonatology, Renmin Hospital of Wuhan University, Wuhan, China.
| |
Collapse
|
2
|
Tataranno ML, Vijlbrief DC, Dudink J, Benders MJNL. Precision Medicine in Neonates: A Tailored Approach to Neonatal Brain Injury. Front Pediatr 2021; 9:634092. [PMID: 34095022 PMCID: PMC8171663 DOI: 10.3389/fped.2021.634092] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/26/2020] [Accepted: 04/14/2021] [Indexed: 11/27/2022] Open
Abstract
Despite advances in neonatal care to prevent neonatal brain injury and neurodevelopmental impairment, predicting long-term outcome in neonates at risk for brain injury remains difficult. Early prognosis is currently based on cranial ultrasound (CUS), MRI, EEG, NIRS, and/or general movements assessed at specific ages, and predicting outcome in an individual (precision medicine) is not yet possible. New algorithms based on large databases and machine learning applied to clinical, neuromonitoring, and neuroimaging data and genetic analysis and assays measuring multiple biomarkers (omics) can fulfill the needs of modern neonatology. A synergy of all these techniques and the use of automatic quantitative analysis might give clinicians the possibility to provide patient-targeted decision-making for individualized diagnosis, therapy, and outcome prediction. This review will first focus on common neonatal neurological diseases, associated risk factors, and most common treatments. After that, we will discuss how precision medicine and machine learning (ML) approaches could change the future of prediction and prognosis in this field.
Collapse
Affiliation(s)
| | | | | | - Manon J. N. L. Benders
- Department of Neonatology, Wilhelmina Children's Hospital/University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| |
Collapse
|
3
|
Sanchez K, Morgan AT, Slattery JM, Olsen JE, Lee KJ, Anderson PJ, Thompson DK, Doyle LW, Cheong JLY, Spittle AJ. Neuropredictors of oromotor feeding impairment in 12month-old children. Early Hum Dev 2017; 111:49-55. [PMID: 28595097 DOI: 10.1016/j.earlhumdev.2017.05.012] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/30/2016] [Revised: 04/07/2017] [Accepted: 05/30/2017] [Indexed: 11/29/2022]
Abstract
BACKGROUND Feeding impairment is prevalent in children with neurodevelopmental issues. Neuroimaging and neurobehavioral outcomes at term are predictive of later neuromotor impairment, but it is unknown whether they predict feeding impairment. AIMS To determine whether neurobehavior and brain magnetic resonance imaging (MRI) at term predict oromotor feeding at 12 months in preterm and term-born children. STUDY DESIGN Prospective cohort study. SUBJECTS 248 infants (97 born <30 weeks and 151 born at term) recruited at birth. OUTCOME MEASURES Neurobehavioral assessments (General Movements (GMA), Hammersmith Neonatal Neurological Examination (HNNE), Neonatal Intensive Care Unit Network Neurobehavioral Scale (NNNS)); and brain MRI were administered at term-equivalent age. Oromotor feeding was assessed at 12 months corrected age using the Schedule for Oral Motor Assessment. RESULTS 49/227 children had oromotor feeding impairment. Neurobehavior associated with later feeding impairment was: suboptimal NNNS stress (odds ratio [OR] 2.68; 95% confidence interval [CI] 1.20–6.01), non-optimal reflexes (OR 3.33; 95% CI 1.37–8.11) and arousal scales (OR 2.54; 95% CI 1.03–6.27); suboptimal HNNE total (OR 4.69; 95% CI 2.20–10.00), reflexes (OR 2.62; 95% CI 1.06–6.49), and tone scores (OR 3.87; 95% CI 1.45–10.35); and abnormal GMA (OR 2.60; 95% CI 1.21–5.57). Smaller biparietal diameter also predicted feeding impairment (OR 0.88; 95% CI 0.79–0.97). There was little evidence that relationships differed between birth groups. CONCLUSIONS Neurobehavior and biparietal diameter at term are associated with oromotor feeding at 12 months. These results may identify children at greatest risk of oromotor feeding impairment.
Collapse
Affiliation(s)
- Katherine Sanchez
- Murdoch Childrens Research Institute, Parkville, VIC 3052, Australia; University of Melbourne, Parkville, VIC 3052, Australia.
| | - Angela T Morgan
- Murdoch Childrens Research Institute, Parkville, VIC 3052, Australia; University of Melbourne, Parkville, VIC 3052, Australia; Royal Children's Hospital, Parkville, VIC 3052, Australia.
| | | | - Joy E Olsen
- Murdoch Childrens Research Institute, Parkville, VIC 3052, Australia; Royal Women's Hospital, Parkville, VIC 3052, Australia.
| | - Katherine J Lee
- Murdoch Childrens Research Institute, Parkville, VIC 3052, Australia; University of Melbourne, Parkville, VIC 3052, Australia.
| | - Peter J Anderson
- Murdoch Childrens Research Institute, Parkville, VIC 3052, Australia; University of Melbourne, Parkville, VIC 3052, Australia.
| | - Deanne K Thompson
- Murdoch Childrens Research Institute, Parkville, VIC 3052, Australia; University of Melbourne, Parkville, VIC 3052, Australia; Florey Institute of Neuroscience and Mental Health, Parkville, VIC 3052, Australia.
| | - Lex W Doyle
- Murdoch Childrens Research Institute, Parkville, VIC 3052, Australia; University of Melbourne, Parkville, VIC 3052, Australia; Royal Women's Hospital, Parkville, VIC 3052, Australia.
| | - Jeanie L Y Cheong
- Murdoch Childrens Research Institute, Parkville, VIC 3052, Australia; University of Melbourne, Parkville, VIC 3052, Australia; Royal Women's Hospital, Parkville, VIC 3052, Australia.
| | - Alicia J Spittle
- Murdoch Childrens Research Institute, Parkville, VIC 3052, Australia; University of Melbourne, Parkville, VIC 3052, Australia; Royal Women's Hospital, Parkville, VIC 3052, Australia.
| |
Collapse
|
4
|
Malhotra A, Fahey MC, Davies-Tuck M, Wong F, Carse E, Whiteley G, Ditchfield M. Comparison of preterm and term equivalent age MRI for the evaluation of preterm brain injury. J Perinatol 2017; 37:864-868. [PMID: 28383535 DOI: 10.1038/jp.2017.39] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/09/2016] [Revised: 02/21/2017] [Accepted: 03/02/2017] [Indexed: 12/18/2022]
Abstract
OBJECTIVE To compare information obtained from preterm magnetic resonance imaging (MRI; 31-34 weeks) brain scan to that done at term equivalent age. STUDY DESIGN Prospective observational study of premature infants with evidence or suspicion of parenchymal brain injury on cranial ultrasound. Brain injury on two scans scored using a scoring system and analyzed. RESULTS Fourteen infants with a median (range) gestation at birth of 28 (25-29) weeks and birth weight of 1254 (680-1557) grams were studied. There was a strong correlation between the brain injury scores for the two scans (Spearman ρ=0.87, P=0.001) with excellent agreement between two radiologists (interclass correlation coefficient 0.9-0.94). There was also a high level of agreement between the preterm and term MRI two scores (Intraclass correlation coefficient, 0.79 (0.53-0.94)). CONCLUSIONS Preterm MRI is a feasible option for the assessment of preterm brain injury and analysis of data obtained from scan at preterm age is comparable to that obtained at term equivalent age.
Collapse
Affiliation(s)
- A Malhotra
- Monash Newborn, Monash Children's Hospital, Melbourne, Victoria, Australia.,The Ritchie Centre, Hudson Institute of Medical Research, Melbourne, Victoria, Australia.,Department of Paediatrics, Monash University, Melbourne, Victoria, Australia
| | - M C Fahey
- The Ritchie Centre, Hudson Institute of Medical Research, Melbourne, Victoria, Australia.,Department of Paediatrics, Monash University, Melbourne, Victoria, Australia
| | - M Davies-Tuck
- The Ritchie Centre, Hudson Institute of Medical Research, Melbourne, Victoria, Australia
| | - F Wong
- Monash Newborn, Monash Children's Hospital, Melbourne, Victoria, Australia.,The Ritchie Centre, Hudson Institute of Medical Research, Melbourne, Victoria, Australia.,Department of Paediatrics, Monash University, Melbourne, Victoria, Australia
| | - E Carse
- Monash Newborn, Monash Children's Hospital, Melbourne, Victoria, Australia
| | - G Whiteley
- Diagnostic Imaging, Monash Health, Melbourne, Victoria, Australia
| | - M Ditchfield
- Department of Paediatrics, Monash University, Melbourne, Victoria, Australia.,Diagnostic Imaging, Monash Health, Melbourne, Victoria, Australia.,Department of Diagnostic Imaging, Monash University, Melbourne, Victoria, Australia
| |
Collapse
|
5
|
Kidowaki S, Morimoto M, Yamada K, Sakai K, Zuiki M, Maeda H, Yamashita S, Morita T, Hasegawa T, Chiyonobu T, Tokuda S, Hosoi H. Longitudinal change in white matter in preterm infants without magnetic resonance imaging abnormalities: Assessment of serial diffusion tensor imaging and their relationship to neurodevelopmental outcomes. Brain Dev 2017; 39:40-47. [PMID: 27543266 DOI: 10.1016/j.braindev.2016.07.007] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/18/2015] [Revised: 03/01/2016] [Accepted: 07/28/2016] [Indexed: 11/15/2022]
Abstract
PURPOSE We used diffusion tensor imaging (DTI) to evaluate longitudinal changes in fractional anisotropy (FA) of white matter tracts in preterm infants without abnormal magnetic resonance imaging (MRI) findings. Imaging was conducted at term equivalent age (TEA) and 1year of corrected age. Furthermore, we assessed correlations between FA and neurodevelopmental outcomes at 3years of corrected age to investigate brain prematurity of preterm infants without MRI abnormalities. METHODS Preterm infants underwent serial MRI at TEA and 1year of corrected age. Of these, 13 infants entered a retrospective study, undergoing neurodevelopmental assessment at 3years of corrected age. These infants were divided into two groups depending on gestational age (GA): <26weeks and ⩾26weeks. DTI-based tractography was performed to obtain the FA of the motor tract, sensory tract, superior cerebellar peduncle, middle cerebellar peduncle, and corpus callosum. FA was compared between two groups, and correlations between FA and neurodevelopmental outcomes were assessed. RESULTS FA of the splenium at TEA was significantly different between the two groups divided according to GA. However, this difference was no longer observed at 1year of corrected age. There was no correlation between FA of the splenium at TEA and neurodevelopmental assessment scores at 3years of corrected age. CONCLUSIONS At TEA, FA of the splenium was lower in younger GA infants without MRI abnormalities, but this may not affect subsequent neurodevelopmental outcomes.
Collapse
Affiliation(s)
- Satoshi Kidowaki
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan
| | - Masafumi Morimoto
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan.
| | - Kei Yamada
- Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Koji Sakai
- Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Masashi Zuiki
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan
| | - Hiroshi Maeda
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan
| | - Satoshi Yamashita
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan
| | - Takashi Morita
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan
| | - Tatsuji Hasegawa
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan
| | - Tomohiro Chiyonobu
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan
| | - Sachiko Tokuda
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan
| | - Hajime Hosoi
- Department of Pediatrics, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kajii-cho Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto 602-8566, Japan
| |
Collapse
|
6
|
Cho HH, Kim IO, Cheon JE, Choi YH, Lee SM, Kim WS. Changes in brain magnetic resonance imaging patterns for preterm infants after introduction of a magnetic resonance-compatible incubator coil system: 5-year experience at a single institution. Eur J Radiol 2016; 85:1564-8. [PMID: 27501889 DOI: 10.1016/j.ejrad.2016.06.007] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2016] [Revised: 05/31/2016] [Accepted: 06/07/2016] [Indexed: 10/21/2022]
Abstract
OBJECTIVE To evaluate the changes in using patterns of brain magnetic resonance imaging (MRI) in preterm infants after introduction of a MR-compatible incubator coil system. MATERIALS AND METHODS Brain MRIs for preterm infants with the MR-compatible incubator coil from March 2010 to July 2014 (n=154, group A) were compared with MRIs prior to the introduction of the incubator coil, from March 2005 to February 2010 (n=65, group B). Clinical data, MRI findings, acquisition time, and incidence of adverse events during the study were retrospectively reviewed. For the qualitative analysis of the examinations, the presence of motion artefact, spatial resolution, and overall image quality were assessed. Signal uniformity of each sequence was evaluated for a quantitative comparison. RESULTS Comparing with group B, Group A was significantly younger (36+3 vs. 38+3 weeks, p<0.001), had a significantly lower body weight (2006.6 and 2390.3g respectively; p<0.001) at the time of MRI, and had shorter time interval (54.3±2.6 vs. 70.5±4.4days, p=0.002) between birth and examination. Abnormal findings were noted more frequently in group A (n=100, 65%) than in B (n=24, 37%. p=0.001) with a significantly higher incidence of diffusion restriction (n=21, 13.6% vs. n=4, 6.2%, p=0.034). Mean image acquisition time was significantly shorter in group A (21.4±4.5 vs. 25.4±5.5min, p<0.001) with significant lower adverse events during MRI (n=26, 40 vs. n=6, 3.9%, p<0.001). Group A exhibited significantly less motion artefact, better spatial resolution, and better overall image quality with decreased signal variation than group B (all p<0.001). CONCLUSION Application of the MR-compatible incubator for preterm brain MRI evaluation is safer and provides more timely evaluation of preterm infants with better image quality.
Collapse
Affiliation(s)
- Hyun-Hae Cho
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 110-744, Republic of Korea
| | - In-One Kim
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 110-744, Republic of Korea; Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 110-799, Republic of Korea; Institute of Radiation Medicine, Seoul National University Medical Research Center, 103 Daehak-ro, Jongno-gu, Seoul, 110-799, Republic of Korea.
| | - Jung-Eun Cheon
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 110-744, Republic of Korea; Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 110-799, Republic of Korea; Institute of Radiation Medicine, Seoul National University Medical Research Center, 103 Daehak-ro, Jongno-gu, Seoul, 110-799, Republic of Korea
| | - Young Hun Choi
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 110-744, Republic of Korea; Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 110-799, Republic of Korea
| | - So Mi Lee
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 110-744, Republic of Korea
| | - Woo Sun Kim
- Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 110-744, Republic of Korea; Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 110-799, Republic of Korea; Institute of Radiation Medicine, Seoul National University Medical Research Center, 103 Daehak-ro, Jongno-gu, Seoul, 110-799, Republic of Korea
| |
Collapse
|